@inproceedings{bb242700,
AUTHOR = "Dong, X.Y. and Bao, J.M. and Zheng, Y.L. and Zhang, T. and Chen, D.D. and Yang, H. and Zeng, M. and Zhang, W.M. and Yuan, L. and Chen, D. and Wen, F. and Yu, N.H.",
TITLE = "MaskCLIP: Masked Self-Distillation Advances Contrastive
Language-Image Pretraining",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10995-11005",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237616"}
@inproceedings{bb242701,
AUTHOR = "Xie, C.W. and Sun, S.Y. and Xiong, X. and Zheng, Y. and Zhao, D.L. and Zhou, J.R.",
TITLE = "RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "19265-19274",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237617"}
@inproceedings{bb242702,
AUTHOR = "Chen, P.J. and Li, Q. and Biaz, S. and Bui, T. and Nguyen, A.",
TITLE = "gScoreCAM: What Objects Is CLIP Looking At?",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "IV:588-604",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237618"}
@inproceedings{bb242703,
AUTHOR = "Wang, R. and Duan, X.Y. and Kang, G.L. and Liu, J.Z. and Lin, S.H. and Xu, S. and Lv, J. and Zhang, B.C.",
TITLE = "AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "3654-3663",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237619"}
@inproceedings{bb242704,
AUTHOR = "Rasheed, H. and Khattak, M.U. and Maaz, M. and Khan, S. and Khan, F.S.",
TITLE = "Fine-tuned CLIP Models are Efficient Video Learners",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6545-6554",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237620"}
@inproceedings{bb242705,
AUTHOR = "Liu, R. and Huang, J.J. and Li, G. and Feng, J.S. and Wu, X.L. and Li, T.H.",
TITLE = "Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge
Transferring",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6555-6564",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237621"}
@inproceedings{bb242706,
AUTHOR = "Tschannen, M. and Mustafa, B. and Houlsby, N.",
TITLE = "CLIPPO: Image-and-Language Understanding from Pixels Only",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "11006-11017",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237622"}
@inproceedings{bb242707,
AUTHOR = "Zhou, Z.Q. and Lei, Y.J. and Zhang, B. and Liu, L.Q. and Liu, Y.F.",
TITLE = "ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "11175-11185",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237623"}
@inproceedings{bb242708,
AUTHOR = "He, W.B. and Jamonnak, S. and Gou, L. and Ren, L.",
TITLE = "CLIP-S4: Language-Guided Self-Supervised Semantic Segmentation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "11207-11216",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237624"}
@inproceedings{bb242709,
AUTHOR = "Huang, Z.X. and Jampani, V. and Thai, A. and Li, Y.Z. and Stojanov, S. and Rehg, J.M.",
TITLE = "ShapeClipper: Scalable 3D Shape Learning from Single-View Images via
Geometric and CLIP-Based Consistency",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "12912-12922",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237625"}
@inproceedings{bb242710,
AUTHOR = "Zeng, Y.H. and Jiang, C.H. and Mao, J.G. and Han, J.H. and Ye, C.Q. and Huang, Q.Q. and Yeung, D.Y. and Yang, Z. and Liang, X.D. and Xu, H.",
TITLE = "CLIP2: Contrastive Language-Image-Point Pretraining from Real-World
Point Cloud Data",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "15244-15253",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237626"}
@inproceedings{bb242711,
AUTHOR = "Lin, Y.Q. and Chen, M.H. and Wang, W.X. and Wu, B. and Li, K. and Lin, B.B. and Liu, H.F. and He, X.F.",
TITLE = "CLIP is Also an Efficient Segmenter: A Text-Driven Approach for
Weakly Supervised Semantic Segmentation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "15305-15314",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237627"}
@inproceedings{bb242712,
AUTHOR = "Sanghi, A. and Fu, R. and Liu, V. and Willis, K.D.D. and Shayani, H. and Khasahmadi, A.H. and Sridhar, S. and Ritchie, D.",
TITLE = "CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse
Shapes from Natural Language",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18339-18348",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237628"}
@inproceedings{bb242713,
AUTHOR = "Pei, R.J. and Liu, J.Z. and Li, W.M. and Shao, B. and Xu, S. and Dai, P. and Lu, J.W. and Yan, Y.",
TITLE = "CLIPPING: Distilling CLIP-Based Models with a Student Base for
Video-Language Retrieval",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18983-18992",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237629"}
@inproceedings{bb242714,
AUTHOR = "Jeong, J. and Zou, Y. and Kim, T. and Zhang, D.Q. and Ravichandran, A. and Dabeer, O.",
TITLE = "WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "19606-19616",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237630"}
@inproceedings{bb242715,
AUTHOR = "Shamshad, F. and Naseer, M. and Nandakumar, K.",
TITLE = "CLIP2Protect: Protecting Facial Privacy Using Text-Guided Makeup via
Adversarial Latent Search",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "20595-20605",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237631"}
@inproceedings{bb242716,
AUTHOR = "Chen, Y.H. and Qi, X. and Wang, J.A. and Zhang, L.",
TITLE = "DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP
Training",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22648-22657",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237632"}
@inproceedings{bb242717,
AUTHOR = "Wasim, S.T. and Naseer, M. and Khan, S. and Khan, F.S. and Shah, M.",
TITLE = "Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "23034-23044",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237633"}
@inproceedings{bb242718,
AUTHOR = "Parelli, M. and Delitzas, A. and Hars, N. and Vlassis, G. and Anagnostidis, S. and Bachmann, G. and Hofmann, T.",
TITLE = "CLIP-Guided Vision-Language Pre-training for Question Answering in 3D
Scenes",
BOOKTITLE = ODRUM23,
YEAR = "2023",
PAGES = "5607-5612",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237634"}
@inproceedings{bb242719,
AUTHOR = "Ning, S. and Qiu, L.T. and Liu, Y.F. and He, X.M.",
TITLE = "HOICLIP: Efficient Knowledge Transfer for HOI Detection with
Vision-Language Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "23507-23517",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237635"}
@inproceedings{bb242720,
AUTHOR = "Yao, L.W. and Han, J.H. and Liang, X.D. and Xu, D. and Zhang, W. and Li, Z.G. and Xu, H.",
TITLE = "DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via
Word-Region Alignment",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "23497-23506",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237636"}
@inproceedings{bb242721,
AUTHOR = "Singha, M. and Jha, A. and Solanki, B. and Bose, S. and Banerjee, B.",
TITLE = "APPLeNet: Visual Attention Parameterized Prompt Learning for Few-Shot
Remote Sensing Image Generalization using CLIP",
BOOKTITLE = EarthVision23,
YEAR = "2023",
PAGES = "2024-2034",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237637"}
@inproceedings{bb242722,
AUTHOR = "Gannamaneni, S.S. and Sadaghiani, A. and Rao, R.P. and Mock, M. and Akila, M.",
TITLE = "Investigating CLIP Performance for Meta-data Generation in AD
Datasets",
BOOKTITLE = SAIAD23,
YEAR = "2023",
PAGES = "3840-3850",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237638"}
@inproceedings{bb242723,
AUTHOR = "Chen, R.N. and Liu, Y.Q. and Kong, L.D. and Zhu, X.G. and Ma, Y.X. and Li, Y.K. and Hou, Y.N. and Qiao, Y. and Wang, W.P.",
TITLE = "CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "7020-7030",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237639"}
@inproceedings{bb242724,
AUTHOR = "Ni, B.L. and Peng, H.W. and Chen, M.H. and Zhang, S.Y. and Meng, G.F. and Fu, J.L. and Xiang, S.M. and Ling, H.B.",
TITLE = "Expanding Language-Image Pretrained Models for General Video
Recognition",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "IV:1-18",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237640"}
@inproceedings{bb242725,
AUTHOR = "Zhang, R.R. and Zhang, W. and Fang, R.Y. and Gao, P. and Li, K.C. and Dai, J.F. and Qiao, Y. and Li, H.S.",
TITLE = "Tip-Adapter: Training-Free Adaption of CLIP for Few-Shot Classification",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXV:493-510",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237641"}
@inproceedings{bb242726,
AUTHOR = "Yang, J. and Duan, J.L. and Tran, S. and Xu, Y. and Chanda, S. and Chen, L.Q. and Zeng, B. and Chilimbi, T. and Huang, J.Z.",
TITLE = "Vision-Language Pre-Training with Triple Contrastive Learning",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15650-15659",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237642"}
@inproceedings{bb242727,
AUTHOR = "Guo, X.Y. and Duan, J.L. and Kuo, C.C.J. and Gichoya, J.W. and Banerjee, I.",
TITLE = "Augmenting Vision Language Pretraining by Learning Codebook with
Visual Semantics",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "4779-4785",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237643"}
@inproceedings{bb242728,
AUTHOR = "Zhou, C. and Loy, C.C. and Dai, B.",
TITLE = "Extract Free Dense Labels from CLIP",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXVIII:696-712",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237644"}
@inproceedings{bb242729,
AUTHOR = "Lin, Z. and Geng, S.J. and Zhang, R.R. and Gao, P. and de Melo, G. and Wang, X.G. and Dai, J.F. and Qiao, Y. and Li, H.S.",
TITLE = "Frozen CLIP Models are Efficient Video Learners",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXV:388-404",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237645"}
@inproceedings{bb242730,
AUTHOR = "Rao, Y.M. and Zhao, W.L. and Chen, G.Y. and Tang, Y.S. and Zhu, Z. and Huang, G. and Zhou, J. and Lu, J.W.",
TITLE = "DenseCLIP: Language-Guided Dense Prediction with Context-Aware
Prompting",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "18061-18070",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237646"}
@inproceedings{bb242731,
AUTHOR = "Kwon, G. and Ye, J.C.",
TITLE = "CLIPstyler: Image Style Transfer with a Single Text Condition",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "18041-18050",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237647"}
@inproceedings{bb242732,
AUTHOR = "Khandelwal, A. and Weihs, L. and Mottaghi, R. and Kembhavi, A.",
TITLE = "Simple but Effective: CLIP Embeddings for Embodied AI",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "14809-14818",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237648"}
@inproceedings{bb242733,
AUTHOR = "Ma, H.Y. and Zhao, H. and Lin, Z. and Kale, A. and Wang, Z.Y. and Yu, T. and Gu, J.X. and Choudhary, S. and Xie, X.H.",
TITLE = "EI-CLIP: Entity-aware Interventional Contrastive Learning for
E-commerce Cross-modal Retrieval",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "18030-18040",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237649"}
@inproceedings{bb242734,
AUTHOR = "Barraco, M. and Cornia, M. and Cascianelli, S. and Baraldi, L. and Cucchiara, R.",
TITLE = "The Unreasonable Effectiveness of CLIP Features for Image Captioning:
An Experimental Analysis",
BOOKTITLE = MULA22,
YEAR = "2022",
PAGES = "4661-4669",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237650"}
@inproceedings{bb242735,
AUTHOR = "Tevet, G. and Gordon, B. and Hertz, A. and Bermano, A.H. and Cohen Or, D.",
TITLE = "MotionCLIP: Exposing Human Motion Generation to CLIP Space",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXII:358-374",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237651"}
@inproceedings{bb242736,
AUTHOR = "Materzynska, J. and Torralba, A. and Bau, D.",
TITLE = "Disentangling visual and written concepts in CLIP",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "16389-16398",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237652"}
@inproceedings{bb242737,
AUTHOR = "Li, M. and Xu, R. and Wang, S. and Zhou, L. and Lin, X.D. and Zhu, C.G. and Zeng, M. and Ji, H. and Chang, S.F.",
TITLE = "CLIP-Event: Connecting Text and Images with Event Structures",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "16399-16408",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237653"}
@inproceedings{bb242738,
AUTHOR = "Zhong, Y. and Yang, J.W. and Zhang, P.C. and Li, C.Y. and Codella, N. and Li, L.H. and Zhou, L. and Dai, X. and Yuan, L. and Li, Y. and Gao, J.F.",
TITLE = "RegionCLIP: Region-based Language-Image Pretraining",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "16772-16782",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237654"}
@inproceedings{bb242739,
AUTHOR = "Patashnik, O. and Wu, Z.Z. and Shechtman, E. and Cohen Or, D. and Lischinski, D.",
TITLE = "StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "2065-2074",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803clip3.html#TT237655"}
@article{bb242740,
AUTHOR = "Su, H.H. and Chen, T.W. and Kao, C.C. and Hsu, W.H. and Chien, S.Y.",
TITLE = "Preference-Aware View Recommendation System for Scenic Photos Based on
Bag-of-Aesthetics-Preserving Features",
JOURNAL = MultMed,
VOLUME = "14",
YEAR = "2012",
NUMBER = "3",
PAGES = "833-843",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237656"}
@article{bb242741,
AUTHOR = "Chen, L. and Xu, D. and Tsang, I.W. and Luo, J.",
TITLE = "Tag-Based Image Retrieval Improved by Augmented Features and
Group-Based Refinement",
JOURNAL = MultMed,
VOLUME = "14",
YEAR = "2012",
NUMBER = "4",
PAGES = "1057-1067",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237657"}
@article{bb242742,
AUTHOR = "Chen, L. and Xu, D. and Tsang, I.W. and Li, X.",
TITLE = "Spectral Embedded Hashing for Scalable Image Retrieval",
JOURNAL = Cyber,
VOLUME = "44",
YEAR = "2014",
NUMBER = "7",
MONTH = "July",
PAGES = "1180-1190",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237658"}
@article{bb242743,
AUTHOR = "Jiao, B. and Yang, L. and Xu, J. and Tian, Q. and Wu, F.",
TITLE = "Visually Summarizing Web Pages Through Internal and External Images",
JOURNAL = MultMed,
VOLUME = "14",
YEAR = "2012",
NUMBER = "6",
PAGES = "1673-1683",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237659"}
@article{bb242744,
AUTHOR = "Sawant, N. and Wang, J.Z. and Li, J.",
TITLE = "Enhancing Training Collections for Image Annotation:
An Instance-Weighted Mixture Modeling Approach",
JOURNAL = IP,
VOLUME = "22",
YEAR = "2013",
NUMBER = "9",
PAGES = "3562-3577",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237660"}
@article{bb242745,
AUTHOR = "Tian, J. and Huang, Y. and Guo, Z. and Qi, X. and Chen, Z. and Huang, T.",
TITLE = "A Multi-Modal Topic Model for Image Annotation Using Text Analysis",
JOURNAL = SPLetters,
VOLUME = "22",
YEAR = "2015",
NUMBER = "7",
MONTH = "July",
PAGES = "886-890",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237661"}
@article{bb242746,
AUTHOR = "Rodriguez Vaamonde, S. and Torresani, L. and Fitzgibbon, A.W.",
TITLE = "What Can Pictures Tell Us About Web Pages? Improving Document Search
Using Images",
JOURNAL = PAMI,
VOLUME = "37",
YEAR = "2015",
NUMBER = "6",
MONTH = "June",
PAGES = "1274-1285",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237662"}
@article{bb242747,
AUTHOR = "Tirkaz, C. and Eisenstein, J. and Sezgin, T.M. and Yanikoglu, B.A.",
TITLE = "Identifying visual attributes for object recognition from text and
taxonomy",
JOURNAL = CVIU,
VOLUME = "137",
YEAR = "2015",
NUMBER = "1",
PAGES = "12-23",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237663"}
@article{bb242748,
AUTHOR = "Lu, Y.J. and Yang, L. and Yang, K. and Rui, Y.",
TITLE = "Mining Latent Attributes From Click-Through Logs for Image
Recognition",
JOURNAL = MultMed,
VOLUME = "17",
YEAR = "2015",
NUMBER = "8",
MONTH = "August",
PAGES = "1213-1224",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237664"}
@article{bb242749,
AUTHOR = "Fu, J. and Wang, J. and Rui, Y. and Wang, X. and Mei, T. and Lu, H.",
TITLE = "Image Tag Refinement With View-Dependent Concept Representations",
JOURNAL = CirSysVideo,
VOLUME = "25",
YEAR = "2015",
NUMBER = "8",
MONTH = "August",
PAGES = "1409-1422",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237665"}
@article{bb242750,
AUTHOR = "Belongie, S. and Perona, P.",
TITLE = "Visipedia circa 2015",
JOURNAL = PRL,
VOLUME = "72",
YEAR = "2016",
NUMBER = "1",
PAGES = "15-24",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237666"}
@article{bb242751,
AUTHOR = "Niu, L. and Li, W. and Xu, D.",
TITLE = "Exploiting Privileged Information from Web Data for Action and Event
Recognition",
JOURNAL = IJCV,
VOLUME = "118",
YEAR = "2016",
NUMBER = "2",
MONTH = "June",
PAGES = "130-150",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237667"}
@inproceedings{bb242752,
AUTHOR = "Li, W. and Niu, L. and Xu, D.",
TITLE = "Exploiting Privileged Information from Web Data for Image
Categorization",
BOOKTITLE = ECCV14,
YEAR = "2014",
PAGES = "V: 437-452",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237668"}
@article{bb242753,
AUTHOR = "Sejal, D. and Rashmi, V. and Venugopal, K.R. and Iyengar, S.S. and Patnaik, L.M.",
TITLE = "Image recommendation based on keyword relevance using absorbing Markov
chain and image features",
JOURNAL = MultInfoRetr,
VOLUME = "5",
YEAR = "2016",
NUMBER = "3",
MONTH = "September",
PAGES = "185-199",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237669"}
@article{bb242754,
AUTHOR = "Yan, Y. and Nie, F.P. and Li, W. and Gao, C.Q. and Yang, Y. and Xu, D.",
TITLE = "Image Classification by Cross-Media Active Learning with Privileged
Information",
JOURNAL = MultMed,
VOLUME = "18",
YEAR = "2016",
NUMBER = "12",
MONTH = "December",
PAGES = "2494-2502",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237670"}
@article{bb242755,
AUTHOR = "Qian, X. and Li, C. and Lan, K. and Hou, X. and Li, Z. and Han, J.",
TITLE = "POI Summarization by Aesthetics Evaluation From Crowd Source Social
Media",
JOURNAL = IP,
VOLUME = "27",
YEAR = "2018",
NUMBER = "3",
MONTH = "March",
PAGES = "1178-1189",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237671"}
@article{bb242756,
AUTHOR = "Li, Z.C. and Tang, J.H. and Mei, T.",
TITLE = "Deep Collaborative Embedding for Social Image Understanding",
JOURNAL = PAMI,
VOLUME = "41",
YEAR = "2019",
NUMBER = "9",
MONTH = "Sep",
PAGES = "2070-2083",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237672"}
@article{bb242757,
AUTHOR = "Zheng, C.M. and Wu, Z.W. and Wang, T. and Cai, Y. and Li, Q.",
TITLE = "Object-Aware Multimodal Named Entity Recognition in Social Media
Posts With Adversarial Learning",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "2520-2532",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237673"}
@article{bb242758,
AUTHOR = "Park, J.Y. and Ryu, D.J. and Nam, K.W. and Jang, I. and Jang, M. and Lee, Y.",
TITLE = "DeepDBSCAN: Deep Density-Based Clustering for Geo-Tagged Photos",
JOURNAL = IJGI,
VOLUME = "10",
YEAR = "2021",
NUMBER = "8",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237674"}
@article{bb242759,
AUTHOR = "Zheng, C.Q. and Zhu, L. and Cheng, Z.Y. and Li, J.J. and Liu, A.A.",
TITLE = "Adaptive Partial Multi-View Hashing for Efficient Social Image
Retrieval",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "4079-4092",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237675"}
@inproceedings{bb242760,
AUTHOR = "Bendou, Y. and Ouasfi, A. and Gripon, V. and Boukhayma, A.",
TITLE = "ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large
Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "25092-25102",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237676"}
@inproceedings{bb242761,
AUTHOR = "Dziadzio, S. and Udandarao, V. and Roth, K. and Prabhu, A. and Akata, Z. and Albanie, S. and Bethge, M.",
TITLE = "How to Merge Your Multimodal Models Over Time?",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "20479-20491",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237677"}
@inproceedings{bb242762,
AUTHOR = "Liu, Z.J. and Stent, S. and Li, J. and Gideon, J. and Han, S.",
TITLE = "LocTex: Learning Data-Efficient Visual Representations from Localized
Textual Supervision",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "2147-2156",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237678"}
@inproceedings{bb242763,
AUTHOR = "Desai, K. and Johnson, J.",
TITLE = "VirTex: Learning Visual Representations from Textual Annotations",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "11157-11168",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237679"}
@inproceedings{bb242764,
AUTHOR = "Kenigsfield, G.S. and El Yaniv, R.",
TITLE = "TranstextNet: Transducing Text for Recognizing Unseen Visual
Relationships",
BOOKTITLE = WACV21,
YEAR = "2021",
PAGES = "1954-1963",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237680"}
@inproceedings{bb242765,
AUTHOR = "Tesan, T. and Coscia, P. and Ballan, L.",
TITLE = "A CNN-RNN Framework for Image Annotation from Visual Cues and Social
Network Metadata",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "231-238",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237681"}
@inproceedings{bb242766,
AUTHOR = "Yang, J.K. and Feng, L.T. and Chen, W.R. and Yan, X.P. and Zheng, H. and Luo, P. and Zhang, W.",
TITLE = "Webly Supervised Image Classification with Self-Contained Confidence",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "VIII:779-795",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237682"}
@inproceedings{bb242767,
AUTHOR = "Long, C.J. and Collins, R. and Swears, E. and Hoogs, A.",
TITLE = "Deep Neural Networks in Fully Connected CRF for Image Labeling with
Social Network Metadata",
BOOKTITLE = WACV19,
YEAR = "2019",
PAGES = "1607-1615",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237683"}
@inproceedings{bb242768,
AUTHOR = "Tu, Y. and Niu, L. and Chen, J.J. and Cheng, D.W. and Zhang, L.Q.",
TITLE = "Learning From Web Data With Self-Organizing Memory Module",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "12843-12852",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237684"}
@inproceedings{bb242769,
AUTHOR = "Niu, L. and Tang, Q.T. and Veeraraghavan, A. and Sabharwal, A.",
TITLE = "Learning from Noisy Web Data with Category-Level Supervision",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7689-7698",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237685"}
@inproceedings{bb242770,
AUTHOR = "Guo, S. and Huang, W.L. and Zhang, H.Z. and Zhuang, C.F. and Dong, D. and Scott, M.R. and Huang, D.L.",
TITLE = "CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "X: 139-154",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237686"}
@inproceedings{bb242771,
AUTHOR = "Chang, X.O. and Xiang, T. and Hospedales, T.M.",
TITLE = "L_1 Graph Based Sparse Model for Label De-noising",
BOOKTITLE = BMVC16,
YEAR = "2016",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237687"}
@inproceedings{bb242772,
AUTHOR = "Vadicamo, L. and Carrara, F. and Cimino, A. and Cresci, S. and Dell'Orletta, F. and Falchi, F. and Tesconi, M.",
TITLE = "Cross-Media Learning for Image Sentiment Analysis in the Wild",
BOOKTITLE = WSM17,
YEAR = "2017",
PAGES = "308-317",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237688"}
@inproceedings{bb242773,
AUTHOR = "Fernandez, D. and Varas, D. and Espadaler, J. and Masuda, I. and Ferreira, J. and Woodward, A. and Rodriguez, D. and Giro i Nieto, X. and Riveiro, J.C. and Bou, E.",
TITLE = "ViTS: Video Tagging System from Massive Web Multimedia Collections",
BOOKTITLE = WSM17,
YEAR = "2017",
PAGES = "337-346",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237689"}
@inproceedings{bb242774,
AUTHOR = "Goyal, R. and Kahou, S.E. and Michalski, V. and Materzynska, J. and Westphal, S. and Kim, H. and Haenel, V. and Fruend, I. and Yianilos, P. and Mueller Freitag, M. and Hoppe, F. and Thurau, C. and Bax, I. and Memisevic, R.",
TITLE = "The 'Something Something' Video Database for Learning and Evaluating
Visual Common Sense",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "5843-5851",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237690"}
@inproceedings{bb242775,
AUTHOR = "Gomez, L. and Patel, Y. and Rusinol, M. and Karatzas, D. and Jawahar, C.V.",
TITLE = "Self-Supervised Learning of Visual Features through Embedding Images
into Text Topic Spaces",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "2017-2026",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237691"}
@inproceedings{bb242776,
AUTHOR = "Eskevich, M. and Larson, M. and Aly, R. and Sabetghadam, S. and Jones, G.J.F. and Ordelman, R. and Huet, B.",
TITLE = "Multimodal Video-to-Video Linking:
Turning to the Crowd for Insight and Evaluation",
BOOKTITLE = MMMod17,
YEAR = "2017",
PAGES = "II: 280-292",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237692"}
@inproceedings{bb242777,
AUTHOR = "Bois, R. and Vukotic, V. and Simon, A.R. and Sicre, R. and Raymond, C. and Sebillot, P. and Gravier, G.",
TITLE = "Exploiting Multimodality in Video Hyperlinking to Improve Target
Diversity",
BOOKTITLE = MMMod17,
YEAR = "2017",
PAGES = "II: 185-197",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237693"}
@inproceedings{bb242778,
AUTHOR = "Izadinia, H. and Sadeghi, F. and Divvala, S.K. and Hajishirzi, H. and Choi, Y. and Farhadi, A.",
TITLE = "Segment-Phrase Table for Semantic Segmentation, Visual Entailment and
Paraphrasing",
BOOKTITLE = ICCV15,
YEAR = "2015",
PAGES = "10-18",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237694"}
@inproceedings{bb242779,
AUTHOR = "Hou, Y.Q.",
TITLE = "Image Annotation Incorporating Low-Rankness, Tag and Visual Correlation
and Inhomogeneous Errors",
BOOKTITLE = ISVC15,
YEAR = "2015",
PAGES = "I: 71-81",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237695"}
@inproceedings{bb242780,
AUTHOR = "Yao, Y.Z. and Zhang, J. and Hua, X.S. and Shen, F.M. and Tang, Z.M.",
TITLE = "Extracting Visual Knowledge from the Internet:
Making Sense of Image Data",
BOOKTITLE = MMMod16,
YEAR = "2016",
PAGES = "I: 862-873",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237696"}
@inproceedings{bb242781,
AUTHOR = "Jas, M. and Parikh, D.",
TITLE = "Image specificity",
BOOKTITLE = CVPR15,
YEAR = "2015",
PAGES = "2727-2736",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237697"}
@inproceedings{bb242782,
AUTHOR = "Johns, E. and Aodha, O.M. and Brostow, G.J.",
TITLE = "Becoming the expert: Interactive multi-class machine teaching",
BOOKTITLE = CVPR15,
YEAR = "2015",
PAGES = "2616-2624",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237698"}
@inproceedings{bb242783,
AUTHOR = "Russakovsky, O. and Li, L.J. and Fei Fei, L.",
TITLE = "Best of both worlds:
Human-machine collaboration for object annotation",
BOOKTITLE = CVPR15,
YEAR = "2015",
PAGES = "2121-2131",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237699"}
@inproceedings{bb242784,
AUTHOR = "Abdulhak, S.A. and Riviera, W. and Zeni, N. and Cristani, M. and Ferrario, R. and Cristani, M.",
TITLE = "Semantic-Analysis Object Recognition:
Automatic Training Set Generation Using Textual Tags",
BOOKTITLE = CVONT14,
YEAR = "2014",
PAGES = "309-322",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237700"}
@inproceedings{bb242785,
AUTHOR = "He, Y.H. and Wang, J. and Xiang, S.M. and Pan, C.H.",
TITLE = "Image annotation via learning the image-label interrelations",
BOOKTITLE = ICIP14,
YEAR = "2014",
PAGES = "3102-3106",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237701"}
@inproceedings{bb242786,
AUTHOR = "Jhuo, I.H. and Weng, L.",
TITLE = "Image auto-annotation by exploiting web information",
BOOKTITLE = ICIP14,
YEAR = "2014",
PAGES = "3052-3056",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237702"}
@inproceedings{bb242787,
AUTHOR = "Safadi, B. and Sahuguet, M. and Huet, B.",
TITLE = "Linking text and visual concepts semantically for cross modal
multimedia search",
BOOKTITLE = ICIP14,
YEAR = "2014",
PAGES = "3077-3081",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237703"}
@inproceedings{bb242788,
AUTHOR = "Xue, J. and Du, Y. and Shui, H.",
TITLE = "Semantic Correlation Mining between Images and Texts with Global
Semantics and Local Mapping",
BOOKTITLE = MMMod15,
YEAR = "2015",
PAGES = "II: 427-435",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237704"}
@inproceedings{bb242789,
AUTHOR = "Verma, Y. and Jawahar, C.V.",
TITLE = "Im2Text and Text2Im:
Associating Images and Texts for Cross-Modal Retrieval",
BOOKTITLE = BMVC14,
YEAR = "2014",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237705"}
@inproceedings{bb242790,
AUTHOR = "Feng, Z. and Feng, S.H. and Jin, R. and Jain, A.K.",
TITLE = "Image Tag Completion by Noisy Matrix Recovery",
BOOKTITLE = ECCV14,
YEAR = "2014",
PAGES = "VII: 424-438",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237706"}
@inproceedings{bb242791,
AUTHOR = "Radu, A.L. and Ionescu, B. and Menendez, M. and Stottinger, J. and Giunchiglia, F. and de Angeli, A.",
TITLE = "A Hybrid Machine-Crowd Approach to Photo Retrieval Result
Diversification",
BOOKTITLE = MMMod14,
YEAR = "2014",
PAGES = "I: 25-36",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237707"}
@inproceedings{bb242792,
AUTHOR = "Wang, C.X. and Song, Z. and Feng, S.H. and Lang, C.Y. and Yan, S.C.",
TITLE = "A novel image tag saliency ranking algorithm based on sparse
representation",
BOOKTITLE = VCIP13,
YEAR = "2013",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237708"}
@inproceedings{bb242793,
AUTHOR = "Mishra, A. and Alahari, K. and Jawahar, C.V.",
TITLE = "Image Retrieval Using Textual Cues",
BOOKTITLE = ICCV13,
YEAR = "2013",
PAGES = "3040-3047",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237709"}
@inproceedings{bb242794,
AUTHOR = "Padilla, S. and Halley, F. and Robb, D.A.",
TITLE = "Intuitive Large Image Database Browsing Using Perceptual Similarity
Enriched by Crowds",
BOOKTITLE = CAIP13,
YEAR = "2013",
PAGES = "II:169-176",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237710"}
@inproceedings{bb242795,
AUTHOR = "Lin, J. and Duan, L.Y. and Yuan, J.S. and Li, Q.Y. and Luo, S.W.",
TITLE = "Learning sparse tag patterns for social image classification",
BOOKTITLE = ICIP12,
YEAR = "2012",
PAGES = "2881-2884",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237711"}
@inproceedings{bb242796,
AUTHOR = "Truong, B.Q. and Sun, A. and Bhowmick, S.S.",
TITLE = "Content is still king: the effect of neighbor voting schemes on tag
relevance for social image retrieval",
BOOKTITLE = ICMR12,
YEAR = "2012",
PAGES = "9",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237712"}
@inproceedings{bb242797,
AUTHOR = "Mousselly Sergieh, H. and Doller, M. and Egyed Zsigmond, E. and Gianini, G. and Kosch, H. and Pinon, J.M.",
TITLE = "Tag Relatedness Using Laplacian Score Feature Selection and Adapted
Jensen-Shannon Divergence",
BOOKTITLE = MMMod14,
YEAR = "2014",
PAGES = "I: 159-171",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237713"}
@inproceedings{bb242798,
AUTHOR = "Mousselly Sergieh, H. and Gianini, G. and Doller, M. and Kosch, H. and Egyed Zsigmond, E. and Pinon, J.M.",
TITLE = "Geo-based automatic image annotation",
BOOKTITLE = ICMR12,
YEAR = "2012",
PAGES = "46",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237714"}
@inproceedings{bb242799,
AUTHOR = "Hradis, M. and Kolar, M. and Lanik, A. and Kral, J. and Zemcik, P. and Smrz, P.",
TITLE = "Annotating Images with Suggestions: User Study of a Tagging System",
BOOKTITLE = ACIVS12,
YEAR = "2012",
PAGES = "155-166",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803we1.html#TT237715"}
Last update:Apr 6, 2026 at 11:28:57